Kies de Nederlandse taal
Course module: 400817-M-6
RM: Structural Equation Modeling & Anal.
Course info
Course module400817-M-6
Credits (ECTS)6
CategoryMA (Master)
Course typeCourse
Language of instructionEnglish
Offered byTilburg University; Tilburg School of Social and Behavioral Sciences; TSB: Methodology and Statistics; Methodology and Statistics;
Is part of
M Individual Differences and Assessment (research)
M Social and Behavioural Sciences (research)
dr. I. Schwabe
Other course modules lecturer
Academic year2020
Starting block
Course mode
RemarksCaution: this information is subject to change
Registration openfrom 12/10/2020 up to and including 20/08/2021
Upon completion of this course, students can:
  • define key SEM concepts and concepts relevant to the modeling of longitudinal data, as presented in the course materials (knowledge)
  • list the assumptions of SEM (knowledge)
  • explain the general logic of estimating SEM models and evaluation of model fit (comprehension)
  • apply rules for model identification of simple and advanced SEM models (application)
  • summarize the most often-used model fit statistics in SEM (comprehension)
  • choose the most appropriate estimator for a SEM model, depending on the nature of the data at hand (application)
  • summarize the rationale of the following models that can be estimated with SEM: first- or second-order CFA models, multiple group analysis and measurement invariance testing, MIMIC modeling, modeling of Common Method Variance, Modeling of Panel Data, Trait-State-Occasion modeling, Multilevel Modeling for Change, Latent Growth Modeling (comprehension)
  • specify and estimate a simple or advanced SEM model (see point 7) or multilevel regression model for longitudinal data, evaluate its fit, and suggest statistically sound and substantiated model re-specification (application, evaluation)
  • evaluate if a published SEM analysis that was reported in a journal in the field of social or behavioral sciences includes sufficient detail for replication of the reported models and suggest possible model improvements, and re-estimate the published models as far as possible (evaluation, synthesis)
The purpose of this course is to introduce research master students to a general statistical framework that brings together multiple regression and factor analysis: the Structural Equation Modeling (SEM) framework. Until now, research master students have been trained in estimating multiple regression models and factor analysis models separately. However, it is possible to estimate such modeling elements (a structural and measurement part) simultaneously within one model, and evaluate the fit of such a model to the data. Mastering this statistical approach will (1) allow students to tackle new exciting research questions in their disciplines and (2) allow them to understand substantive research papers in the social and behavioral sciences or methodological research papers in which SEM is applied or further developed. In the first four weeks of the course, we introduce students to the basic concepts of SEM. In the remaining three weeks, we consider the logic, estimation, and interpretation of more advanced SEM or related (multilevel regression) models that are particularly useful for the analysis of longitudinal data.

Required Prerequisites
Only for students who are qualified for the Research Master
Contact person
dr. I. Schwabe
Timetable information
RM: Structural Equation Modeling & Anal.
Written test opportunities
Written test opportunities (HIST)
MC Computer tentamen / MC Computer ExamEXAM_01BLOK 2116-12-2020
MC Computer tentamen / MC Computer ExamEXAM_01BLOK 2221-01-2021
Required materials
To be announced
Relevant articles and book chapters on (longitudinal) structural equation modeling. Details on this literature will be announced at the beginning of the course via CANVAS.
Title:Structural Equation Modeling with lavaan (2019)
Author:Kamel Gana and Guillaume Broc
Publisher:ISTE Ltd and John Wiley & Sons, Inc.
Recommended materials

MC Computer Exam

Kies de Nederlandse taal